{"id":"https://openalex.org/W4413839272","doi":"https://doi.org/10.1007/s10462-025-11362-z","title":"DAoG: decayed adaptation over gradients for parameter-free step size control","display_name":"DAoG: decayed adaptation over gradients for parameter-free step size control","publication_year":2025,"publication_date":"2025-08-30","ids":{"openalex":"https://openalex.org/W4413839272","doi":"https://doi.org/10.1007/s10462-025-11362-z"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-025-11362-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11362-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11362-z.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11362-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056548830","display_name":"Yifan Zhang","orcid":"https://orcid.org/0000-0002-9182-6267"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Zhang","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017835678","display_name":"Di Zhao","orcid":"https://orcid.org/0000-0002-0876-5126"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Zhao","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, 100191, China","School of Mathematical Sciences, Beihang University, Beijing, 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Mathematical Sciences, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413696","display_name":"Hongyi Li","orcid":"https://orcid.org/0000-0002-6891-0858"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongyi Li","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, 100191, China","School of Mathematical Sciences, Beihang University, Beijing, 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Mathematical Sciences, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083970977","display_name":"Chengwei Pan","orcid":"https://orcid.org/0000-0002-7882-7644"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengwei Pan","raw_affiliation_strings":["Key Laboratory of Mathematics, Informatics and Behavioral Semantics, Ministry of Education, Beijing, 100191, China","School of Artificial Intelligence, Beihang University, Beijing, 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Mathematics, Informatics and Behavioral Semantics, Ministry of Education, Beijing, 100191, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100413696"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08686878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"58","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7426767349243164},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5911853909492493},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.38597074151039124},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3569929003715515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22889479994773865},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12866735458374023},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.05384206771850586}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7426767349243164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5911853909492493},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.38597074151039124},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3569929003715515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22889479994773865},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12866735458374023},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.05384206771850586}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10462-025-11362-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11362-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11362-z.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10462-025-11362-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11362-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11362-z.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G6820710298","display_name":"\u7535\u78c1\u5e72\u6270\u4fe1\u53f7\u7684\u6570\u5b66\u8868\u5f81\u65b9\u6cd5\u4e0e\u7406\u8bba\u7814\u7a76","funder_award_id":"61771001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413839272.pdf","grobid_xml":"https://content.openalex.org/works/W4413839272.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2251939518","https://openalex.org/W2533598788","https://openalex.org/W2740721704","https://openalex.org/W2747680751","https://openalex.org/W2923014074","https://openalex.org/W2941799245","https://openalex.org/W2963446712","https://openalex.org/W3160518394","https://openalex.org/W3183827394","https://openalex.org/W3190730109","https://openalex.org/W4210647952","https://openalex.org/W4313595515","https://openalex.org/W4320005661","https://openalex.org/W4376104443","https://openalex.org/W4391881209","https://openalex.org/W4401363756","https://openalex.org/W4404001897","https://openalex.org/W4407174419","https://openalex.org/W4407330542"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"As":[0],"the":[1,12,36,39,68,86,145,149,173,243,252,259],"scale":[2],"of":[3,14,38,57,67,213,261],"parameters":[4],"in":[5,31,35,74,136,196,211,229,249,255,265],"deep":[6,266],"learning":[7],"models":[8,17],"continues":[9],"to":[10,169,172],"grow,":[11],"cost":[13],"training":[15,46,112],"such":[16],"increases":[18],"accordingly,":[19],"posing":[20],"increasingly":[21],"significant":[22],"challenges":[23],"for":[24,144],"stochastic":[25],"optimization":[26,33,59,125,151,157,263],"methods.":[27],"A":[28],"central":[29],"issue":[30,248],"gradient-based":[32],"lies":[34,135],"selection":[37],"step":[40,69,140,175,246],"size,":[41],"whose":[42],"appropriateness":[43],"directly":[44],"affects":[45],"efficiency":[47],"and":[48,80,97,159,188,200,209,216,235,251],"model":[49,109,160],"performance.":[50,218],"To":[51],"address":[52],"this":[53],"issue,":[54],"a":[55,122,138,163],"series":[56],"parameter-free":[58,124,150,262],"methods":[60,264],"that":[61,127,180,204,239],"do":[62],"not":[63],"require":[64],"manual":[65],"tuning":[66],"size":[70,141,247],"have":[71],"been":[72],"proposed":[73],"recent":[75],"years.":[76],"Among":[77],"them,":[78],"DoG":[79,96,208,250],"its":[81],"improved":[82],"variant":[83],"DoWG":[84,98,210],"are":[85],"most":[87],"representative.":[88],"Despite":[89],"demonstrating":[90],"strong":[91],"performance":[92,102],"across":[93,193],"various":[94],"tasks,":[95],"still":[99],"suffer":[100],"from":[101],"instability":[103,253],"or":[104,111,223],"slow":[105],"convergence":[106,184,214],"under":[107,186],"certain":[108],"architectures":[110],"conditions.":[113,190],"This":[114],"paper":[115],"introduces":[116],"Decayed":[117],"Adaptation":[118],"over":[119],"Gradients":[120],"(DAoG),":[121],"novel":[123],"method":[126],"systematically":[128],"addresses":[129],"these":[130],"limitations.":[131],"Our":[132],"key":[133],"innovation":[134],"incorporating":[137],"principled":[139],"decay":[142],"mechanism":[143],"first":[146],"time":[147],"within":[148],"framework,":[152],"which":[153],"substantially":[154],"enhances":[155],"both":[156,207],"stability":[158],"generalization.":[161],"Additionally,":[162],"parameter":[164],"compression":[165],"strategy":[166],"is":[167],"employed":[168],"reduce":[170],"sensitivity":[171],"initial":[174],"size.":[176],"Theoretical":[177],"analysis":[178],"demonstrates":[179],"DAoG":[181,205,240],"exhibits":[182],"favorable":[183],"properties":[185],"L-smooth":[187],"G-Lipschitz":[189],"Empirical":[191],"studies":[192],"representative":[194],"tasks":[195],"natural":[197],"language":[198],"processing":[199],"computer":[201],"vision":[202],"demonstrate":[203],"outperforms":[206],"terms":[212],"speed":[215],"generalization":[217],"Notably,":[219],"it":[220],"even":[221],"rivals":[222],"surpasses":[224],"Adam":[225],"with":[226],"cosine":[227],"annealing":[228],"several":[230],"challenging":[231],"scenarios.":[232],"These":[233],"theoretical":[234],"experimental":[236],"results":[237],"suggest":[238],"effectively":[241],"mitigates":[242],"overly":[244],"conservative":[245],"problem":[254],"DoWG,":[256],"thereby":[257],"advancing":[258],"development":[260],"learning.":[267]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}